Main Content

Object Analysis

Detect edges, circles and lines; trace boundaries; perform quadtree decomposition

In an image, an edge is a curve that follows a path of rapid change in image intensity. Edges are often associated with the boundaries of objects in a scene. Different algorithms are suited for detecting edges of straight lines, round objects, or arbitrarily shaped regions. Conversely, you can detect homogenous blocks that lack edges.


expand all

bwboundariesTrace region boundaries in binary image
bwtraceboundaryTrace object in binary image
visboundariesPlot region boundaries
imfindcirclesFind circles using circular Hough transform
viscirclesCreate circle
edgeFind edges in 2-D grayscale image
edge3Find edges in 3-D grayscale volume
imgradientFind gradient magnitude and direction of 2-D image
imgradientxyFind directional gradients of 2-D image
imgradient3Find gradient magnitude and direction of 3-D image
imgradientxyzFind directional gradients of 3-D image
houghHough transform
houghlinesExtract line segments based on Hough transform
houghpeaksIdentify peaks in Hough transform
radonRadon transform
iradonInverse Radon transform
qtdecompQuadtree decomposition
qtgetblkBlock values in quadtree decomposition
qtsetblkSet block values in quadtree decomposition


  • Edge Detection

    Edge detection is a technique for finding the boundaries of objects within an image.

  • Boundary Tracing in Images

    You can display the boundaries of a single object or of all objects in an image.

  • Hough Transform

    The Hough transform detects lines in an image, including lines tilted at arbitrary angles from vertical and horizontal. The Hough transform tends to be quick, but can exhibit artifacts.

  • Detect Lines Using Radon Transform

    This example shows how to detect lines and identify the strongest lines in an image using the Radon transform.

  • Quadtree Decomposition

    Quadtree decomposition is useful as a first step in adaptive image compression. The decomposition involves subdividing an image into homogenous blocks.